Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding

• URL: http://arxiv.org/abs/2505.12605v1
• Date: Mon, 19 May 2025 01:40:25 GMT
• Title: Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding
• Authors: Thong Nguyen, Zhiyuan Hu, Xu Lin, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan,
• Abstract summary: We conduct a thorough empirical study to demystify crucial components that influence the temporal understanding of LVLMs.<n>Building on these insights, we propose a temporal-oriented recipe that encompasses temporal-oriented training schemes and an upscaled interface.
• Score: 26.932018092345192
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent years have witnessed outstanding advances of large vision-language models (LVLMs). In order to tackle video understanding, most of them depend upon their implicit temporal understanding capacity. As such, they have not deciphered important components that contribute to temporal understanding ability, which might limit the potential of these LVLMs for video understanding. In this work, we conduct a thorough empirical study to demystify crucial components that influence the temporal understanding of LVLMs. Our empirical study reveals that significant impacts are centered around the intermediate interface between the visual encoder and the large language model. Building on these insights, we propose a temporal-oriented recipe that encompasses temporal-oriented training schemes and an upscaled interface. Our final model developed using our recipe significantly enhances previous LVLMs on standard video understanding tasks.

Related papers

• Infinite Video Understanding [50.78256932424239]
  We argue that framing Infinite Video Understanding as a blue-sky research objective provides a vital north star for the multimedia.<n>We outline the core challenges and key research directions towards achieving this transformative capability.
  arXiv  Detail & Related papers  (2025-07-11T23:07:04Z)
• Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities [54.94982467313341]
  Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems.<n>We set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking.
  arXiv  Detail & Related papers  (2025-07-10T15:26:41Z)
• Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency [56.475612147721264]
  We propose a dual-reward formulation that supervises both semantic and temporal reasoning through discrete and continuous reward signals.<n>We evaluate our approach across eight representative video understanding tasks, including VideoQA, Temporal Video Grounding, and Grounded VideoQA.<n>Results underscore the importance of reward design and data selection in advancing reasoning-centric video understanding with MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T17:28:26Z)
• MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding [55.32878803528196]
  Video temporal understanding is crucial for multimodal large language models (MLLMs) to reason over events in videos.<n>We propose MUSEG, a novel RL-based method that enhances temporal understanding by introducing timestamp-aware multi-segment grounding.<n>To facilitate effective learning, we design a customized RL training recipe with phased rewards that progressively guides the model toward temporally grounded reasoning.
  arXiv  Detail & Related papers  (2025-05-27T04:50:07Z)
• Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models [53.13731845500678]
  We introduce a novel metric, $Rank_e$, to quantify the effect of vision encoder's prior knowledge on MLLM performance.<n>We propose VisPRE, a two-stage training framework that explicitly incorporates prior knowledge at the vision encoder level.<n> Experimental results demonstrate that augmenting vision encoder's prior knowledge substantially boosts the visual understanding capabilities of MLLMs.
  arXiv  Detail & Related papers  (2025-03-23T11:33:09Z)
• Do Language Models Understand Time? [2.290956583394892]
  Large language models (LLMs) have revolutionized video-based computer vision applications, including action recognition, anomaly detection, and summarization.<n>This work critically examines the role of LLMs in video processing, with a specific focus on their temporal reasoning capabilities.<n>We analyze challenges posed by existing video datasets, including biases, lack of temporal annotations, and domain-specific limitations that constrain the temporal understanding of LLMs.
  arXiv  Detail & Related papers  (2024-12-18T13:38:06Z)
• Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge [24.538839144639653]
  Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components. These models frequently encounter a core issue of "cognitive misalignment" between the vision encoder (VE) and the large language model (LLM)
  arXiv  Detail & Related papers  (2024-11-25T18:33:14Z)
• From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding [52.696422425058245]
  MultiModal Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks.<n>Our paper focuses on the substantial differences and unique challenges posed by long video understanding compared to static image and short video understanding.
  arXiv  Detail & Related papers  (2024-09-27T17:38:36Z)
• TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations [23.188508465235717]
  We propose two strategies to enhance the model's capability in video understanding tasks. The first approach focuses on the enhancement of Rotary Position Embedding (RoPE) with Temporal-Aware Dual RoPE. The second approach involves enhancing the Attention Mask with the Frame-wise Block Causal Attention Mask.
  arXiv  Detail & Related papers  (2024-09-05T02:54:17Z)
• Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies [69.28082193942991]
  This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet previously overlooked video reasoning skills. utilizing tropes from movie storytelling, TiM evaluates the reasoning capabilities of state-of-the-art LLM-based approaches. To address these deficiencies, we propose Face-Enhanced Viper of Role Interactions (FEVoRI) and Context Query Reduction (ConQueR)
  arXiv  Detail & Related papers  (2024-06-16T12:58:31Z)
• RelationVLM: Making Large Vision-Language Models Understand Visual Relations [66.70252936043688]
  We present RelationVLM, a large vision-language model capable of comprehending various levels and types of relations whether across multiple images or within a video. Specifically, we devise a multi-stage relation-aware training scheme and a series of corresponding data configuration strategies to bestow RelationVLM with the capabilities of understanding semantic relations.
  arXiv  Detail & Related papers  (2024-03-19T15:01:19Z)
• Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge [47.750073410717604]
  We introduce Temporal Grounding Bridge (TGB), a novel framework that bootstraps MLLMs with advanced temporal grounding capabilities. We validate TGB across seven video benchmarks and demonstrate substantial performance improvements compared with prior MLLMs. Our model, initially trained on sequences of four frames, effectively handles sequences up to 16 longer without sacrificing performance.
  arXiv  Detail & Related papers  (2024-02-25T10:27:46Z)
• VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models [27.280311932711847]
  We present VITATECS, a diagnostic VIdeo-Text dAtaset for the evaluation of TEmporal Concept underStanding. We first introduce a fine-grained taxonomy of temporal concepts in natural language in order to diagnose the capability of VidLMs to comprehend different temporal aspects. We generate counterfactual video descriptions that differ from the original one only in the specified temporal aspect.
  arXiv  Detail & Related papers  (2023-11-29T07:15:34Z)
• PALM: Predicting Actions through Language Models [74.10147822693791]
  We introduce PALM, an approach that tackles the task of long-term action anticipation. Our method incorporates an action recognition model to track previous action sequences and a vision-language model to articulate relevant environmental details. Our experimental results demonstrate that PALM surpasses the state-of-the-art methods in the task of long-term action anticipation.
  arXiv  Detail & Related papers  (2023-11-29T02:17:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.